Recommender systems have become pervasive on the web, shaping the way users see information and thus the decisions they make. As these systems get more complex, there is a growing need for transparency. In this paper, we study the problem of generating and visualizing personalized explanations for hybrid recommender systems, which incorporate many different data sources. We build upon a hybrid probabilistic graphical model and develop an approach to generate real-time recommendations along with personalized explanations. To study the benefits of explanations for hybrid recommender systems, we conduct a crowd-sourced user study where our system generates personalized recommendations and explanations for real users of the last.fm music platform. We experiment with 1) different explanation styles (e.g., user-based, item-based), 2) manipulating the number of explanation styles presented, and 3) manipulating the presentation format (e.g., textual vs. visual). We apply a mixed model statistical analysis to consider user personality traits as a control variable and demonstrate the usefulness of our approach in creating personalized hybrid explanations with different style, number, and format.
Description
Personalized explanations for hybrid recommender systems
%0 Conference Paper
%1 Kouki:2019:PEH:3301275.3302306
%A Kouki, Pigi
%A Schaffer, James
%A Pujara, Jay
%A O'Donovan, John
%A Getoor, Lise
%B Proceedings of the 24th International Conference on Intelligent User Interfaces
%C New York, NY, USA
%D 2019
%I ACM
%K explanation iui2019 recommender
%P 379--390
%R 10.1145/3301275.3302306
%T Personalized Explanations for Hybrid Recommender Systems
%U http://doi.acm.org/10.1145/3301275.3302306
%X Recommender systems have become pervasive on the web, shaping the way users see information and thus the decisions they make. As these systems get more complex, there is a growing need for transparency. In this paper, we study the problem of generating and visualizing personalized explanations for hybrid recommender systems, which incorporate many different data sources. We build upon a hybrid probabilistic graphical model and develop an approach to generate real-time recommendations along with personalized explanations. To study the benefits of explanations for hybrid recommender systems, we conduct a crowd-sourced user study where our system generates personalized recommendations and explanations for real users of the last.fm music platform. We experiment with 1) different explanation styles (e.g., user-based, item-based), 2) manipulating the number of explanation styles presented, and 3) manipulating the presentation format (e.g., textual vs. visual). We apply a mixed model statistical analysis to consider user personality traits as a control variable and demonstrate the usefulness of our approach in creating personalized hybrid explanations with different style, number, and format.
%@ 978-1-4503-6272-6
@inproceedings{Kouki:2019:PEH:3301275.3302306,
abstract = {Recommender systems have become pervasive on the web, shaping the way users see information and thus the decisions they make. As these systems get more complex, there is a growing need for transparency. In this paper, we study the problem of generating and visualizing personalized explanations for hybrid recommender systems, which incorporate many different data sources. We build upon a hybrid probabilistic graphical model and develop an approach to generate real-time recommendations along with personalized explanations. To study the benefits of explanations for hybrid recommender systems, we conduct a crowd-sourced user study where our system generates personalized recommendations and explanations for real users of the last.fm music platform. We experiment with 1) different explanation styles (e.g., user-based, item-based), 2) manipulating the number of explanation styles presented, and 3) manipulating the presentation format (e.g., textual vs. visual). We apply a mixed model statistical analysis to consider user personality traits as a control variable and demonstrate the usefulness of our approach in creating personalized hybrid explanations with different style, number, and format.},
acmid = {3302306},
added-at = {2019-03-07T18:01:10.000+0100},
address = {New York, NY, USA},
author = {Kouki, Pigi and Schaffer, James and Pujara, Jay and O'Donovan, John and Getoor, Lise},
biburl = {https://www.bibsonomy.org/bibtex/293e19cc9b222e0e4feece180371ed4eb/brusilovsky},
booktitle = {Proceedings of the 24th International Conference on Intelligent User Interfaces},
description = {Personalized explanations for hybrid recommender systems},
doi = {10.1145/3301275.3302306},
interhash = {8acef653220e23b75eed3a8379fd9d79},
intrahash = {93e19cc9b222e0e4feece180371ed4eb},
isbn = {978-1-4503-6272-6},
keywords = {explanation iui2019 recommender},
location = {Marina del Ray, California},
numpages = {12},
pages = {379--390},
publisher = {ACM},
series = {IUI '19},
timestamp = {2019-06-09T09:31:20.000+0200},
title = {Personalized Explanations for Hybrid Recommender Systems},
url = {http://doi.acm.org/10.1145/3301275.3302306},
year = 2019
}